From wiki-suite
JIT wiki-context loader: searches project wiki + global wiki for topic. Loads raw pages — no synthesis. Unified retrieval interface for all knowledge tiers. AUTOMATICALLY INVOKE when: "what do we know about", "load context for", "pull in wiki context", "find in wiki", "look up in the wiki", "load the wiki page for", "what's in the wiki about", "load knowledge about" PROACTIVELY INVOKE when: wiki-notify injects WIKI_PARTIAL previews and current task involves planning/designing/debugging/answering those topics — full-page retrieval required before substantive work. Also invoke when entering plan-mode for features touching wiki-documented domains. NOT for: synthesized answers (/wiki-query), source ingestion (/wiki-ingest)
How this skill is triggered — by the user, by Claude, or both
Slash command
/wiki-suite:wiki-loadsonnetThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Load pages from the wiki into context on demand. Searches both the project wiki
Load pages from the wiki into context on demand. Searches both the project wiki
AND the global wiki (~/.claude/wiki/topics/). Returns raw pages — no synthesis.
Use /wiki-query if you want a synthesized answer with citations.
From $ARGUMENTS, extract:
TOPIC: the search term (required)GLOBAL_ONLY: true if --global flagPROJECT_ONLY: true if --project flagFind REPO_ROOT via git rev-parse --show-toplevel if in a repo (for project tier).
If REPO_ROOT was found and $REPO_ROOT/.wiki/log.md exists, append a log entry via Bash:
echo "[$(date '+%Y-%m-%d %H:%M')] WIKI_LOAD session:${CLAUDE_CODE_SESSION_ID:0:8}: /wiki-load $ARGUMENTS" >> "$REPO_ROOT/.wiki/log.md"
If not GLOBAL_ONLY and in a git repo with a wiki:
Locate WIKI_DIR (search for .wiki/log.md from git root — matches hook sentinel).
If found:
.wiki/entities/ for TOPIC (case-insensitive) — select up to 3 best matches.wiki/sources/ for TOPIC — select up to 2 additional matchesCheck both paths (backward compat during reflect pipeline migration):
~/.claude/wiki/topics/~/.claude/reflection-knowledge/topics/Grep for TOPIC across both directories. Select up to 2 best matches.
Read each matched page in full (max 7 pages total: up to 5 project + 2 global).
Print using the output-format character vocabulary:
╔═══════════════════════════════════════╗
║ 📚 wiki-load — [TOPIC] ║
╚═══════════════════════════════════════╝
Project wiki ([M] pages)
├─ 🏠 entities/[slug].md [first line of overview]
├─ 🏠 entities/[slug].md [first line of overview]
└─ 🏠 sources/[slug].md [first line of summary]
Global wiki ([K] topics)
├─ 🌐 topics/[slug].md [first line of summary]
└─ 🌐 topics/[slug].md [first line of summary]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[N] pages loaded | /wiki-query for synthesis
After the summary, print each page's full content (this is the actual context injection).
If no matches in either tier:
⚠ No wiki pages found for '[TOPIC]'
▸ /wiki-ingest <source> to add project knowledge
◉ Global topics auto-added after sessions discussing [TOPIC]
/wiki-load loads raw pages — the content appears in context for you to reference/wiki-query/wiki-load --global <topic> is the replacement for /reflect <topic>npx claudepluginhub whichguy/claude-craft --plugin wiki-suiteFetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Applies a firm's KYC/AML rules grid to parsed onboarding records: assigns risk rating, checks required documents, outputs rule outcomes with citations, and routes for escalation.
Generates daily or weekly digests of activity from connected sources (chat, email, docs, tasks, CRM), highlighting action items, decisions, mentions, and project updates.